Error Message Improver

• Outcome: Pass
• Latest audit: Sep 10, 2026 · 5:33 AM UTC
• Version: 0.20260910.52416

Overview

This is a documentation-only skill for improving error messages, with no executable code, credential access, persistence, or hidden data handling.

This skill appears safe to install as a lightweight writing/workflow helper. Users should be aware that implicit invocation is enabled and the trigger terms are broad, so it may be selected for general support or debugging requests unless routing is tightened.

A.I.G

Vulnerability Patterns

• Skill Instruction Hijacking: Alters the agent's session goals or safety constraints when the skill loads
• Agent Memory Poisoning: Writes attacker-controlled rules into memory that affect later sessions
• Remote Payload Retrieval and Execution: Fetches external code whose behavior can change after review
• Embedded Malicious Code: Ships malicious scripts inside the skill and executes them locally
• Unauthorized Access and Privilege Escalation: Obtains permissions beyond the task's legitimate needs

SkillSpector

Vulnerability Patterns

• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Trigger Abuse: Overly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• Privilege Escalation: Excessive Permissions, Sudo/Root Execution, Credential Access
• Supply Chain: Unpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (12)

Vague Triggers

High

• Confidence: 98% confidence
• Finding: The trigger sentence is so generic that it can match normal user requests about help, productivity, support, or debugging without clear intent to invoke this specific skill. That creates over-broad activation conditions, increasing the chance the agent routes unrelated conversations into this skill and exposes users to unintended behavior or prompt-scope capture.

Vague Triggers

Medium

• Confidence: 96% confidence
• Finding: The trigger sentences are framed in broad, natural language that overlaps with common user requests, which increases the chance the skill is invoked when the user did not explicitly intend to use it. Unintended invocation can steer conversations, alter outputs, or expose the agent to unnecessary instruction precedence conflicts, especially in environments with automatic skill routing.

Natural-Language Policy Violations

Medium

• Confidence: 91% confidence
• Finding: This file is entirely presented in Simplified Chinese and does not indicate that language choice is optional or that other locales are available from within this document. Under the stated policy, forcing a specific language without opt-in is a natural-language policy concern unless the locale restriction is explicitly justified.

Vague Triggers

Medium

• Confidence: 95% confidence
• Finding: The trigger phrases are generic enough to match many ordinary support, debugging, and productivity requests, which can cause the skill to activate outside the user's explicit intent. Over-broad auto-invocation increases the chance of prompt hijacking at the routing layer, where this skill could be inserted into unrelated conversations and influence outputs unexpectedly.

Vague Triggers

Medium

• Confidence: 95% confidence
• Finding: The skill description includes broad activation terms such as work-productivity, debugging, user feedback, support, and practical workflow language that can match many ordinary requests beyond the specific task of improving error messages. This increases the chance of unintended invocation, which can route users into an irrelevant skill and influence outputs in contexts where the skill was not the best or safest match.

Vague Triggers

Medium

• Confidence: 97% confidence
• Finding: The trigger keywords are highly generic and unconstrained, especially debugging, user feedback, support, and troubleshooting. In a skill-routing system, these terms can cause overbroad matching and accidental activation for many unrelated requests, leading to prompt-scope confusion and misapplication of the skill.

Vague Triggers

Medium

• Confidence: 97% confidence
• Finding: The skill description is framed so broadly that it can match many ordinary productivity, support, and debugging requests rather than a narrowly scoped task. Overbroad routing increases the chance this skill is invoked in unintended contexts, causing prompt-scope confusion, poor task isolation, and potentially bypassing more appropriate specialized skills or guardrails.

Vague Triggers

Medium

• Confidence: 96% confidence
• Finding: The keyword list uses generic terms like work-productivity, debugging, support, and user feedback without contextual qualifiers, which makes accidental invocation likely. In a skill-selection pipeline, this can lead to misrouting of unrelated user requests, expanding the skill's effective authority and increasing the chance of inappropriate instructions or outputs being applied outside its intended domain.

Vague Triggers

Medium

• Confidence: 92% confidence
• Finding: The default prompt uses a very broad, natural-language invocation phrase tied to common support and debugging requests. This increases the chance that the skill is triggered in ordinary conversations without clear user intent, which can cause unintended routing, context injection into the skill, or over-application of the skill in situations where it was not explicitly requested.

Vague Triggers

Medium

• Confidence: 95% confidence
• Finding: Implicit invocation is enabled with no visible trigger constraints, exclusions, or boundary conditions. In a skill focused on broad workplace support topics like error messages, debugging, and user feedback, this makes accidental activation more likely and can cause the system to invoke the skill on unrelated user requests, expanding access to user context and increasing prompt-routing risk.

Vague Triggers

Medium

• Confidence: 93% confidence
• Finding: The usage signals and trigger descriptions do not define clear activation boundaries, so the skill may fire on a wide range of ordinary requests that only loosely relate to troubleshooting or support. In an agent environment, ambiguous routing logic is dangerous because it enables prompt hijacking of benign conversations into a skill with broad authority to shape workflow and outputs.

Natural-Language Policy Violations

Low

• Confidence: 74% confidence
• Finding: The file declares separate English and Chinese instruction and guide files, but does not state how the user's preferred language is selected. This can create a locale-policy ambiguity because a skill may present a language without explicit user opt-in or choice.

Static analysis

No suspicious patterns detected.